Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.6332. Min Act: -0.1700
Data Index: 5818959 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.6019. Min Act: -0.1700
Data Index: 2662165 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.4144. Min Act: -0.1700
Data Index: 370330 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.4144. Min Act: -0.1700
Data Index: 1703116 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.3832. Min Act: -0.1700
Data Index: 337788 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.3832. Min Act: -0.1700
Data Index: 6174048 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.3519. Min Act: -0.1700
Data Index: 7387169 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.3207. Min Act: -0.1700
Data Index: 2696364 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.3207. Min Act: -0.1700
Data Index: 1163523 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.3207. Min Act: -0.1700
Data Index: 573562 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.2894. Min Act: -0.1700
Data Index: 6999709 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.2582. Min Act: -0.1700
Data Index: 3242877 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.2582. Min Act: -0.1700
Data Index: 8300145 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.2269. Min Act: -0.1700
Data Index: 2370453 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.1957. Min Act: -0.1700
Data Index: 7644625 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.1957. Min Act: -0.1700
Data Index: 6539740 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.1644. Min Act: -0.1700
Data Index: 7984695 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.1644. Min Act: -0.1700
Data Index: 2864551 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.1644. Min Act: -0.1700
Data Index: 6539739 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6332. Min Range: -6.6332
Max Act: 6.1644. Min Act: -0.1700
Data Index: 6114097 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19